# Isaac 0.1 API

> Mô hình thị giác-ngôn ngữ trả lời về hình ảnh dưới dạng văn bản, hộp, điểm hoặc đa giác

Nhận `image_url` và `prompt`, rồi trả về phản hồi theo định dạng đặt trong `response_style`. Văn bản phù hợp với chú thích và mô tả, còn kiểu box, point và polygon bổ sung đầu ra định vị. Kết quả gồm đầu ra được tạo, cờ đầu ra một phần, thông báo lỗi nếu có và thông tin sử dụng.

- Model id: `perceptron/isaac-01`
- Made by: Perceptron
- Category: Vision
- Output: text
- Estimated price per run: $0.001 / run (cheapest run $0.001 (1 API credit))
- Run: `POST https://api.doitong.com/v1/run/perceptron/isaac-01`
- Quote: `POST https://api.doitong.com/v1/quote/perceptron/isaac-01`
- Docs page: https://doitong.com/vi/developers/models/perceptron/isaac-01

## Pricing

Price: **$0.001 / run**. Estimated from the typical cost of one run. The quote is exactly what the run charges.

The full example input below costs $0.001 = 1 API credit (1 request × 1 API credits).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.com/v1/quote/perceptron/isaac-01` with the same JSON body returns the exact price for that input; the quote is exactly what a run charges. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

Send either the canonical name or the native field name (not both). Canonical names are the same across models.

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `image_url` | `image` | string (image URL) | yes |  |  | URL xác định hình ảnh cần xử lý. |
| `prompt` |  | string | yes |  |  | Lời nhắc áp dụng cho hình ảnh. |
| `response_style` |  | enum (string) | no | `text` | `text`, `box`, `point`, `polygon` | Chọn định dạng phản hồi hình ảnh: mọi chế độ đều bao gồm văn bản, trong đó box thêm các hộp giới hạn, point thêm các điểm và polygon thêm các đa giác; chỉ text trả về văn bản. Dùng polygon để phân đoạn chi tiết hoặc box để định vị. Dùng text cho mô tả và chú thích; dùng point để đếm nhiều đối tượng. |

File parameters (`image`) take a public `https://` URL, a `data:` URI up to 10 MB, or the `file_url` of an upload from `POST /files`.

## Example input

Required parameters only:

```json
{
  "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

A fuller example:

```json
{
  "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

## Run it

Set `DOITONG_API_KEY` to a key from https://doitong.com/developers/dashboard#keys. `?wait=20` returns the finished request in the same call when it is ready within 20 seconds; otherwise poll `GET /requests/{id}` (it also accepts `?wait=`), or pass `webhook_url`.

### curl

```bash
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/perceptron/isaac-01?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.com/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/perceptron/isaac-01?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
```

### Python

```python
import os
import requests

API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/perceptron/isaac-01", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
```

### MCP

The MCP server at `https://api.doitong.com/v1/mcp` exposes the tools `search_models`, `get_model`, `quote`, `run`, `get_request`, `cancel_request`, `list_requests`, `create_upload` and `get_account`. A `run` call for this model:

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "perceptron/isaac-01",
      "input": {
        "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
      },
      "wait_seconds": 20
    }
  }
}
```

## Response

Every call returns a request object. `status` is one of `queued`, `running`, `succeeded`, `failed`, `canceled`. `outputs` lists the generated files with URLs on our storage (kept forever, or 7 days with `?storage=temporary`; `storage` says which); `output` is the model's own result object with the same URLs.

```json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "perceptron/isaac-01",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 1,
    "usd": "0.001",
    "charged": 1,
    "refunded": 0
  },
  "input": {
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "output": {
    "output": "To determine which car is trying to park into the garage, we need to carefully observe the positions and movements of the vehicles in the image.\n\n1. **Identify the Vehicles**: \n   - There are three vehicles visible: a green truck, an orange car, and a brown car.\n   - The green truck is positioned in front of the garage entrance.\n   - The orange car is parked to the left of the green truck.\n   - The brown car is parked to the right of the green truck.\n\n2. **Analyze the Positions**:\n   - The green truck is directly in front of the garage entrance, suggesting it is in the process of moving towards the entrance.\n   - The orange car is parked parallel to the garage but is not in the path of the green truck.\n   - The brown car is also parked parallel to the garage but is not in the path of the green truck.\n\n3. **Determine the Action**:\n   - Given the position of the green truck directly in front of the garage entrance, it is most likely that the green truck is trying to park into the garage.\n   - The orange and brown cars are already parked and do not appear to be in motion or attempting to park.\n\nTherefore, the car that is trying to park into the garage is the green truck.",
    "partial": false,
    "error": "string",
    "usage": {
      "completion_tokens": 1,
      "prompt_tokens": 1,
      "total_tokens": 1
    }
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `output` | string | Kết quả do mô hình tạo ra. |
| `partial` | boolean | Cho biết đầu ra có chưa hoàn tất hay không. |
| `error` | string \| null | Thông báo mô tả lỗi, nếu có lỗi xảy ra. |
| `usage` | object {completion_tokens, prompt_tokens, total_tokens} \| null | Chi tiết mức sử dụng. |

## Related models

- [Bagel · Understand](https://doitong.com/developers/models/bagel/understand.md) (`bagel/understand`): $0.05 / request
- [Bria Ad Delayer](https://doitong.com/developers/models/bria/ad-delayer.md) (`bria/ad-delayer`): $0.30 / request
- [Florence 2 Large Caption](https://doitong.com/developers/models/florence-2-large/caption.md) (`florence-2-large/caption`): $0.003 / run
- [Florence 2 Large Detailed Caption](https://doitong.com/developers/models/florence-2-large/detailed-caption.md) (`florence-2-large/detailed-caption`): $0.004 / run
- [Florence 2 Large OCR](https://doitong.com/developers/models/florence-2-large/ocr.md) (`florence-2-large/ocr`): $0.003 / run
- [Florence 2 Large Region To Category](https://doitong.com/developers/models/florence-2-large/region-to-category.md) (`florence-2-large/region-to-category`): $0.003 / run
- [Florence-2 Large · More Detailed Caption](https://doitong.com/developers/models/florence-2-large/more-detailed-caption.md) (`florence-2-large/more-detailed-caption`): $0.004 / run
- [Florence-2 Large · Region to Description](https://doitong.com/developers/models/florence-2-large/region-to-description.md) (`florence-2-large/region-to-description`): $0.003 / run

## Links

- HTML page: https://doitong.com/developers/models/perceptron/isaac-01
- All models and guides for AI agents: https://doitong.com/developers/llms.txt
- OpenAPI 3.1 with this model's typed request body: https://doitong.com/developers/openapi.json?model=perceptron/isaac-01
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/perceptron/isaac-01